A comparative study of GEP and an ANN strategy to model engine performance and emission characteristics of a CRDI assisted single cylinder diesel engine under CNG dual-fuel operation

Sumit Roy, Ashmita Ghosh, Ajoy Kumar Das, Rahul Banerjee

Research output: Contribution to journalArticlepeer-review

38 Citations (Scopus)

Abstract

In the present work, the performance and emission parameters of a single cylinder four-stroke CRDI engine under CNG-diesel dual-fuel mode have been modelled by Gene Expression Programming. Based on the experimental data, GEP model was developed to predict BSFCeq, BTE, NOx, PM and HC. Load, fuel injection pressure and CNG energy share were chosen as input parameters for the model. The developed GEP model was capable of predicting the performance and emission parameters with commendable accuracy as observed from correlation coefficients within the range of 0.999368-0.999999. Mean absolute percentage error in the range of 0.036-1.09% along with noticeably low root mean square errors provided an acceptable index of the robustness of the predicted accuracy. In addition, the obtained results were also compared with an ANN model developed on the same parametric ranges wherein the GEP model was observed to be superior in predicting the desired response variables.

Original languageEnglish
Pages (from-to)814-828
Number of pages15
JournalJournal of Natural Gas Science and Engineering
Volume21
Early online date28 Oct 2014
DOIs
Publication statusPublished - 1 Nov 2014
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2014 Elsevier B.V.

Keywords

  • Artificial neural network
  • CNG
  • CRDI
  • Engine performance
  • Exhaust emissions
  • Gene expression programming

ASJC Scopus subject areas

  • Energy Engineering and Power Technology

Fingerprint

Dive into the research topics of 'A comparative study of GEP and an ANN strategy to model engine performance and emission characteristics of a CRDI assisted single cylinder diesel engine under CNG dual-fuel operation'. Together they form a unique fingerprint.

Cite this